{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZWTP4QOWGISCXOQEGH5JDP2G7Q","short_pith_number":"pith:ZWTP4QOW","schema_version":"1.0","canonical_sha256":"cda6fe41d632242bba0431fa91bf46fc2904db8b9039072c095495ba9a8047d9","source":{"kind":"arxiv","id":"2407.11351","version":1},"attestation_state":"computed","paper":{"title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lin Wang, Xu Zheng, Yuanhuiyi Lyu","submitted_at":"2024-07-16T03:34:38Z","abstract_excerpt":"Image modality is not perfect as it often fails in certain conditions, e.g., night and fast motion. This significantly limits the robustness and versatility of existing multi-modal (i.e., Image+X) semantic segmentation methods when confronting modality absence or failure, as often occurred in real-world applications. Inspired by the open-world learning capability of multi-modal vision-language models (MVLMs), we explore a new direction in learning the modality-agnostic representation via knowledge distillation (KD) from MVLMs. Intuitively, we propose Any2Seg, a novel framework that can achieve"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.11351","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T03:34:38Z","cross_cats_sorted":[],"title_canon_sha256":"c229465ce98552879dde77e579d3395ebe665b891ba12e860d5c207eefaaa938","abstract_canon_sha256":"5bcc25e57d450330673371fc70b32b15b4d8080b116a369815dba95419705aac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:22.872800Z","signature_b64":"raqR3Af7KV21KO0xRTXg6JkgogYWU1RSmov6xzk2alfk5f6N3NkB8jVY7m1LUo1Vkq4ID47P+RDktd86lxdwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cda6fe41d632242bba0431fa91bf46fc2904db8b9039072c095495ba9a8047d9","last_reissued_at":"2026-07-05T08:44:22.872480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:22.872480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lin Wang, Xu Zheng, Yuanhuiyi Lyu","submitted_at":"2024-07-16T03:34:38Z","abstract_excerpt":"Image modality is not perfect as it often fails in certain conditions, e.g., night and fast motion. This significantly limits the robustness and versatility of existing multi-modal (i.e., Image+X) semantic segmentation methods when confronting modality absence or failure, as often occurred in real-world applications. Inspired by the open-world learning capability of multi-modal vision-language models (MVLMs), we explore a new direction in learning the modality-agnostic representation via knowledge distillation (KD) from MVLMs. Intuitively, we propose Any2Seg, a novel framework that can achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11351","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.11351/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.11351","created_at":"2026-07-05T08:44:22.872525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11351v1","created_at":"2026-07-05T08:44:22.872525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11351","created_at":"2026-07-05T08:44:22.872525+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWTP4QOWGISC","created_at":"2026-07-05T08:44:22.872525+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWTP4QOWGISCXOQE","created_at":"2026-07-05T08:44:22.872525+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWTP4QOW","created_at":"2026-07-05T08:44:22.872525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.07825","citing_title":"Deep Multimodal Learning with Missing Modality: A Survey","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q","json":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q.json","graph_json":"https://pith.science/api/pith-number/ZWTP4QOWGISCXOQEGH5JDP2G7Q/graph.json","events_json":"https://pith.science/api/pith-number/ZWTP4QOWGISCXOQEGH5JDP2G7Q/events.json","paper":"https://pith.science/paper/ZWTP4QOW"},"agent_actions":{"view_html":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q","download_json":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q.json","view_paper":"https://pith.science/paper/ZWTP4QOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11351&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWTP4QOWGISCXOQEGH5JDP2G7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWTP4QOWGISCXOQEGH5JDP2G7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q/action/storage_attestation","attest_author":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q/action/author_attestation","sign_citation":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q/action/citation_signature","submit_replication":"https://pith.science/pith/ZWTP4QOWGISCXOQEGH5JDP2G7Q/action/replication_record"}},"created_at":"2026-07-05T08:44:22.872525+00:00","updated_at":"2026-07-05T08:44:22.872525+00:00"}